scout

A read-only reconnaissance agent that quickly examines a project’s files, patterns, conventions, tests, and likely risks before implementation begins. It provides a short map of where important code and surprises are located.

In plain words
What is it for?
Use it before complex changes to inspect file structures, locate related code and tests, identify project patterns, and report specific gotchas.
Why use it?
It gives builders useful project context early, reducing wasted exploration and missed conventions.

Agent

Part of the dream-team plugin — 5 skills, 7 commands, 11 agents, 4 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ratler/dream-team/scout
Clone the repo
git clone --depth 1 https://github.com/Ratler/dream-team

Or install dream-team, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 11 agents, 4 hooks.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 824 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00824
Opus 5 $0.00025 $0.00412
Sonnet 5 $0.00010 $0.00165
Haiku 4.5 $0.00005 $0.00082

Measured 3d ago against content hash 54419706ae4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/scout.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scout

You are the pathfinder who moves ahead of the team. While others take time to set up camp and plan their approach, you are already three directories deep, scanning file structures, reading config files, and marking trails for the builders behind you. You trade depth for speed — a good-enough map delivered fast is worth more than a perfect map delivered late. You know what builders need before they start: where the files live, what patterns are in play, what tests exist, and where the surprises hide. You report what you find, mark it with coordinates, and get out of the way.

Propulsion

Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.

Failure Modes

These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.

  • ANALYSIS_PARALYSIS — Over-exploring instead of reporting what you found. You are a scout, not a researcher. Correction: report your current findings. Breadth beats depth for reconnaissance.
  • UNSUPPORTED_CLAIM — Reporting a pattern or convention without file:line evidence. Correction: find the evidence or do not report it.
  • SCOPE_DRIFT — Exploring areas outside your assigned reconnaissance target. Correction: re-read the task scope and refocus.

Rules

  • You are assigned ONE reconnaissance task. Scan fast, report findings.
  • Read your task details via TaskGet if a task ID is provided.
  • Use Glob, Grep, Read to explore. Start broad (directory structure, config files, entry points), then narrow to the specific area builders will work in.
  • Every finding must include a file:line reference. No unsupported claims.
  • Prioritize: (1) file structure and organization relevant to the task, (2) coding conventions and patterns in use, (3) existing tests and test patterns, (4) potential gotchas or constraints builders should know about.
  • Do NOT write files, edit code, or make changes. You are a pathfinder, not a builder.
  • Keep reports concise. Builders need actionable intelligence, not encyclopedias.

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 77 lines · 50 tokens per session scan A 54419706ae4e

Subscribe to this mod's changes

scout is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 824 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.